diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 2ecac000e5da..d35a114c46ed 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1971,7 +1971,10 @@ int i915_reset_engine(struct intel_engine_cs *engine) * process to program RING_MODE, HWSP and re-enable submission. */ ret = engine->init_hw(engine); + if (ret) + goto out; + error->reset_engine_count[engine->id]++; out: return ret; } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 152e30750dd4..90cc63e5ced8 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -917,6 +917,7 @@ struct i915_gpu_state { enum intel_engine_hangcheck_action hangcheck_action; struct i915_address_space *vm; int num_requests; + u32 reset_count; /* position of active request inside the ring */ u32 rq_head, rq_post, rq_tail; @@ -1567,6 +1568,9 @@ struct i915_gpu_error { #define I915_WEDGED (BITS_PER_LONG - 1) #define I915_RESET_ENGINE (I915_WEDGED - I915_NUM_ENGINES) + /** Number of times an engine has been reset */ + u32 reset_engine_count[I915_NUM_ENGINES]; + /** * Waitqueue to signal when a hang is detected. Used to for waiters * to release the struct_mutex for the reset to procede. @@ -3474,6 +3478,12 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error) return READ_ONCE(error->reset_count); } +static inline u32 i915_reset_engine_count(struct i915_gpu_error *error, + struct intel_engine_cs *engine) +{ + return READ_ONCE(error->reset_engine_count[engine->id]); +} + struct drm_i915_gem_request * i915_gem_reset_prepare_engine(struct intel_engine_cs *engine); int i915_gem_reset_prepare(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index e18f350bc364..ae70283470a6 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -463,6 +463,7 @@ static void error_print_engine(struct drm_i915_error_state_buf *m, err_printf(m, " hangcheck action timestamp: %lu, %u ms ago\n", ee->hangcheck_timestamp, jiffies_to_msecs(jiffies - ee->hangcheck_timestamp)); + err_printf(m, " engine reset count: %u\n", ee->reset_count); error_print_request(m, " ELSP[0]: ", &ee->execlist[0]); error_print_request(m, " ELSP[1]: ", &ee->execlist[1]); @@ -1236,6 +1237,8 @@ static void error_record_engine_registers(struct i915_gpu_state *error, ee->hangcheck_timestamp = engine->hangcheck.action_timestamp; ee->hangcheck_action = engine->hangcheck.action; ee->hangcheck_stalled = engine->hangcheck.stalled; + ee->reset_count = i915_reset_engine_count(&dev_priv->gpu_error, + engine); if (USES_PPGTT(dev_priv)) { int i;